Author

Mengnan Du

Observed name: Du, Mengnan

Institutions: New Jersey Institute of Technology, Chinese University of Hong Kong, Chinese University of Hong Kong, Shenzhen

Observed institutions: New Jersey Institute of Technology, Chinese University of Hong Kong, Chinese University of Hong Kong, Shenzhen

OpenAlex ID: A5114452506

Unveiling Project-Specific Bias in Neural Code Models

2024 · Zhiming Li, Yanzhou Li, et al. · Language Resources and Evaluation Conference (LREC) · 5

FinChart-Bench: Benchmarking Financial Chart Comprehension in Vision-Language Models

2026 · Dong Shu, Haoyang Yuan, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting · 2

EvoWeave: Composing Reusable Agent Experience through Operation Level Graphs

2026 · Zhu, Guanhua, Shen, Bo, et al. · arXiv (Cornell University)

STRATA: Self-Maintaining Structured Experience Graphs for Self-Evolving Language Agents

2026 · Zhu, Guanhua, Li, Hanwen, et al. · arXiv (Cornell University)

MM-FinEval: A Multi-Task Multimodal Benchmark for Real-World Financial Forecasting

2026 · Shu, Dong, Liu, Yanguang, et al. · arXiv (Cornell University)

RewardExplainer: Learning Reward Model Explanations from Counterfactual Preference Feedback

2026 · He, Jingyi, Wu, Nier, et al. · arXiv (Cornell University)

BiasReducer: Adaptive Bias Mitigation for Reward Models

2026 · Liu, Shuang, Miao, Yongliang, et al. · arXiv (Cornell University)

Beyond Distribution Matching: Semantics-Consistent Tabular Diffusion with Weak Semantic Priors

2026 · Wang, Yili, Shi, Ruxue, et al. · arXiv (Cornell University)

TAROT: Task-Adaptive Refinement of LLM-prior Graphs for Few-shot Tabular Learning

2026 · Shi, Ruxue, Wang, Yili, et al. · arXiv (Cornell University)

DynaCF: Mitigating Shortcut Learning in Reward Models via Dynamic Counterfactual Sensitivity

2026 · Liu, Fengyuan, Miao, Yongliang, et al. · arXiv (Cornell University)

RASFT: Rollout-Adaptive Supervised Fine-Tuning for Reasoning

2026 · Miao, Yongliang, Liu, Fengyuan, et al. · arXiv (Cornell University)

AdaJudge: Adaptive Multi-Perspective Judging for Reward Modeling

2026 · Association for Computational Linguistics 2026, Du, Mengnan, et al. · Underline Science Inc.

FinCall-Surprise: A Large Scale Multi-modal Benchmark for Earning Surprise Prediction

2026 · Association for Computational Linguistics 2026, Du, Mengnan, et al. · Underline Science Inc.

FinChart-Bench: Benchmarking Financial Chart Comprehension in Vision-Language Models

2026 · Association for Computational Linguistics 2026, Du, Mengnan, et al. · Underline Science Inc.

LLM Agents in Law: Taxonomy, Applications, and Challenges

2026 · Association for Computational Linguistics 2026, Deng, Yujia, et al. · Underline Science Inc.

SAE-FiRE: Enhancing Earnings Surprise Predictions Through Sparse Autoencoder Feature Selection

2026 · Association for Computational Linguistics 2026, Du, Mengnan, et al. · Underline Science Inc.

FaithLM: Towards Faithful Explanations for Large Language Models

2026 · Association for Computational Linguistics 2026, Braverman, Vladimir, et al. · Underline Science Inc.

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering

2026 · Association for Computational Linguistics 2026, Du, Mengnan, et al. · Underline Science Inc.

DeepSieve: Information Sieving via LLM-as-a-Knowledge-Router

2026 · Association for Computational Linguistics 2026, Cheng, Wei, et al. · Underline Science Inc.

SAGE: An Agentic Explainer Framework for Interpreting SAE Features in Language Models

2026 · Association for Computational Linguistics 2026, Du, Mengnan, et al. · Underline Science Inc.

Farther the Shift, Sparser the Representation: Analyzing OOD Mechanisms in LLMs

2026 · Jin, Mingyu, Yin, Yutong, et al. · arXiv (Cornell University)

FinAnchor: Aligned Multi-Model Representations for Financial Prediction

2026 · He, Zirui, Zhang, Huopu, et al. · arXiv (Cornell University)

AdaJudge: Adaptive Multi-Perspective Judging for Reward Modeling

2026 · Miao, Yongliang, Liang, Yangyang, et al. · arXiv (Cornell University)

NeuronScope: A Multi-Agent Framework for Explaining Polysemantic Neurons in Language Models

2026 · Liu, Weiqi, Miao, Yongliang, et al. · arXiv (Cornell University)

SAGE: An Agentic Explainer Framework for Interpreting SAE Features in Language Models

2026 · Jiaojiao Han, Wujiang Xu, et al. · Conference of the European Chapter of the Association for Computational Linguistics

Works count: 31

Citation count: 7

H-index: 2

I10-index: